
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

import csv
import folium as folium
import pycountry
import plotly.express as px #pip install plotly==5.10.0 OR conda install -c plotly plotly=5.10.0
from scipy import stats
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split


#1
data = pd.read_excel('unwto-all-data-download_0.xlsx', sheet_name=None, header = None)
#2 PDF loaded in Appendix
ranking_19 = pd.read_csv('overall_rankings_2019.csv')
#3 JSON loaded in Appendix
region = pd.read_csv('region.csv')
#4 Retrieved in Appendix
countries_interest = pd.read_csv('countries_interest.csv')
#5 Web scraped in Appendix
countries = pd.read_csv('countries.csv', index_col=0)
#6
area = pd.read_csv('API_AG.LND.TOTL.K2_DS2_en_csv_v2_4546125.csv', names = range(67))


#Getting dataframe for outbound departures
outbound_departures = data['Outbound Tourism-Departures']
#Dropping redundant data
outbound_departures = outbound_departures.drop([0,1])
outbound_departures = outbound_departures.drop(outbound_departures.tail(4).index)
outbound_departures = outbound_departures.iloc[: , :-1]
outbound_departures = outbound_departures.drop([0,1,2,4,7,9], axis = 1)
outbound_departures = outbound_departures.reset_index(drop=True)
outbound_departures.columns = outbound_departures.iloc[0]
outbound_departures = outbound_departures[1:]
outbound_departures = outbound_departures[outbound_departures.iloc[:,4]!='Departures']
outbound_departures.iloc[:,0].ffill(inplace = True)
outbound_departures = outbound_departures[outbound_departures.Units.notna()]
#Replacing '..' with NaN
outbound_departures = outbound_departures.replace('..', np.nan)
outbound_departures.iloc[:,1:3] = outbound_departures.iloc[:,1:3].ffill(axis=1)
#Renaming the columns
new_columns = list(outbound_departures.columns.values)
new_columns[0] = 'Countries'
new_columns[1] = 'placeholder'
new_columns[2] = 'Indicators'
outbound_departures.columns = new_columns
outbound_departures = outbound_departures.drop('placeholder', axis = 1)
outbound_departures = outbound_departures.reset_index(drop=True)
#Setting the index
outbound_departures.index = [np.array(outbound_departures['Countries']), np.array(outbound_departures['Indicators'])]
outbound_departures = outbound_departures.drop(['Countries', 'Indicators'], axis = 1)
#Renaming the index
outbound_departures.index.names = ['Countries', 'Indicators']
outbound_departures


#Getting dataframe for inbound departures
inbound_arrivals = data[' Inbound Tourism-Arrivals']
#Dropping redundant data
inbound_arrivals = inbound_arrivals.drop([0,1])
inbound_arrivals = inbound_arrivals.drop(inbound_arrivals.tail(8).index)
inbound_arrivals = inbound_arrivals.iloc[: , :-1]
inbound_arrivals = inbound_arrivals.drop([0,1,2,4,9,10], axis = 1)
inbound_arrivals = inbound_arrivals.reset_index(drop=True)
inbound_arrivals.columns = inbound_arrivals.iloc[0]
inbound_arrivals = inbound_arrivals[1:]
inbound_arrivals = inbound_arrivals[inbound_arrivals.iloc[:,4]!='Arrivals']
inbound_arrivals.iloc[:,0].ffill(inplace = True)
inbound_arrivals = inbound_arrivals[inbound_arrivals.Units.notna()]
#Replacing '..' with NaN
inbound_arrivals = inbound_arrivals.replace('..', np.nan)
inbound_arrivals.iloc[:,1:4] = inbound_arrivals.iloc[:,1:4].ffill(axis=1)
#Renaming the columns
new_columns = list(inbound_arrivals.columns.values)
new_columns[0] = 'Countries'
new_columns[1] = 'placeholder'
new_columns[2] = 'placeholder2'
new_columns[3] = 'Indicators'
inbound_arrivals.columns = new_columns
inbound_arrivals = inbound_arrivals.drop(['placeholder', 'placeholder2'], axis = 1)
inbound_arrivals = inbound_arrivals.reset_index(drop=True)
#Setting the index
inbound_arrivals.index = [np.array(inbound_arrivals['Countries']), np.array(inbound_arrivals['Indicators'])]
#Removing Indicators that are 'of which, cruise passengers' as it is a subset of 'Same-day visitors (excursionists)'
inbound_arrivals = inbound_arrivals[inbound_arrivals.Indicators != 'of which, cruise passengers']
inbound_arrivals = inbound_arrivals.drop(['Countries', 'Indicators'], axis = 1)
#Renaming the index
inbound_arrivals.index.names = ['Countries', 'Indicators']
inbound_arrivals


#Getting dataframe for inbound departures
domestic_trips = data['Domestic Tourism-Trips']
#Dropping redundant data
domestic_trips = domestic_trips.drop([0,1])
domestic_trips = domestic_trips.drop(domestic_trips.tail(4).index)
domestic_trips = domestic_trips.iloc[: , :-1]
domestic_trips = domestic_trips.drop([0,1,2,4,9], axis = 1)
domestic_trips = domestic_trips.reset_index(drop=True)
domestic_trips.columns = domestic_trips.iloc[0]
domestic_trips = domestic_trips[1:]
domestic_trips = domestic_trips[domestic_trips.iloc[:,4]!='Trips']
domestic_trips.iloc[:,0].ffill(inplace = True)
domestic_trips = domestic_trips[domestic_trips.Units.notna()]
#Replacing '..' with NaN
domestic_trips = domestic_trips.replace('..', np.nan)
domestic_trips.iloc[:,1:4] = domestic_trips.iloc[:,1:4].ffill(axis=1)
#Renaming the columns
new_columns = list(domestic_trips.columns.values)
new_columns[0] = 'Countries'
new_columns[1] = 'placeholder'
new_columns[2] = 'placeholder2'
new_columns[3] = 'Indicators'
domestic_trips.columns = new_columns
domestic_trips = domestic_trips.drop(['placeholder', 'placeholder2'], axis = 1)
domestic_trips = domestic_trips.reset_index(drop=True)
#Setting the index
domestic_trips.index = [np.array(domestic_trips['Countries']), np.array(domestic_trips['Indicators'])]
domestic_trips = domestic_trips.drop(['Countries', 'Indicators'], axis = 1)
#Renaming the index
domestic_trips.index.names = ['Countries', 'Indicators']
domestic_trips


#Dropping redundant data
ranking_19 = ranking_19.drop('Unnamed: 0', axis=1)
ranking_19


#Dropping redundant data
region = region.drop('Unnamed: 0', axis=1)
region


countries = countries.reset_index(drop = True)
#Renaming countries' names to match geodata
countries = countries.replace({'name': {'United States': 'United States of America', 'Bahamas': 'The Bahamas', 'Serbia': 'Republic of Serbia', 'Macedonia [FYROM]': 'Macedonia', 'Myanmar [Burma]': 'Myanmar', 'Guinea-Bissau': 'Guinea Bissau', 'Congo [Republic]': 'Republic of the Congo', 'Tanzania': 'United Republic of Tanzania', 'Timor-Leste': 'East Timor'}})
countries


#Renaming 'date' into 'Date'
countries_interest = countries_interest.rename(columns={'date':'Date'})
#Setting Date as the index
countries_interest.set_index('Date', inplace=True)
#Changing the data type of date into datetime
countries_interest.index = pd.to_datetime(countries_interest.index)
countries_interest


#Dropping redundant data
area = area.loc[2:, :63]
area = area.T.set_index(2).T.reset_index(drop = True)
area.columns.name = ''
area = area.drop([1960.0, 'Indicator Name', 'Indicator Code'], axis = 1)
#Changing the data type to float
area[np.arange(1961,2020)] = area[np.arange(1961,2020)].astype('float')
area


#Function to find alpha 2 code of country through its name
def findCountry2(country_name):
    try:
        return pycountry.countries.search_fuzzy(country_name)[0].alpha_2
    except:
        return None


#Function to find alpha 3 code of country through its name
def findCountry3(country_name):
    try:
        return pycountry.countries.search_fuzzy(country_name)[0].alpha_3
    except:
        return None


#Adding up 'Overnights visitors (tourists)' and 'Same-day visitors (excursionists)' to get 'Total departures'
outbound_2 = outbound_departures.reset_index()
outbound_2 = outbound_2[outbound_2['Indicators'] != 'Total departures']
outbound_2 = outbound_2.groupby('Countries').sum()[np.arange(1995,2020)].reset_index()
outbound_2 = outbound_2.set_index('Countries')
outbound_2

outbound = outbound_departures.reset_index()
#Selecting 'Total departures'
outbound = outbound[outbound['Indicators'] == 'Total departures']
outbound = outbound.drop(['Indicators', 'Units', 2020], axis = 1)
outbound = outbound.set_index('Countries')
#Replacing NaN data of outbound with values from outbound_2
outbound = outbound.combine_first(outbound_2).reset_index()
#Changing the units from thounsands to millions
outbound[outbound.select_dtypes(include = ['number']).columns] /= 1000.0
outbound.insert(0, 'Units', 'Millions')
#Setting all 0 to NaN
outbound = outbound.replace({0: np.nan})
#Forward filling before backward filling
outbound[np.arange(1995,2020)] = outbound[np.arange(1995,2020)].ffill(axis = 1).bfill(axis = 1)
#Summing the data
outbound['sum'] = outbound[np.arange(1995,2020)].sum(axis=1)
#Getting alpha 2 code
outbound['country_alpha_2'] = outbound.apply(lambda row: findCountry2(row.Countries) , axis = 1)
#Getting alpha 3 code
outbound['country_alpha_3'] = outbound.apply(lambda row: findCountry3(row.Countries) , axis = 1)
#Merging with countries to get latitude and longitude of each country
outbound = pd.merge(outbound, countries, left_on='country_alpha_2', right_on='country', how='left')
#Merging with region to get region of each country
outbound = pd.merge(outbound, region[['alpha-2', 'region']], left_on='country_alpha_2', right_on='alpha-2', how='left')
#Dropping redundant data
outbound = outbound.drop(['alpha-2', 'country', 'Countries'],axis=1)
#Rearranging the columns
cols = outbound.columns.tolist()
cols = [cols[-2]] + cols[-6:-4] + [cols[-1]] + cols[-4:-2] + cols[:-6]
outbound = outbound[cols]
#Dropping null data
outbound = outbound[outbound['name'].notna()]
#Renaming the column
outbound = outbound.rename(columns={'Units':'units'})
#Sorting through sum
outbound = outbound.sort_values(by='sum', ascending = False)
#Dropping duplicate data
outbound = outbound.drop_duplicates(subset = 'name')
#Resetting index
outbound =  outbound.reset_index(drop = True)
#Setting the alpha 2 code and alpha 3 code specifically for Namibia
outbound.loc[outbound['name'] == 'Namibia', 'country_alpha_2'] = 'NA'
outbound.loc[outbound['name'] == 'Namibia', 'country_alpha_3'] = 'NAM'
outbound


#Adding up 'Overnights visitors (tourists)' and 'Same-day visitors (excursionists)' to get 'Total arrivals'
inbound_2 = inbound_arrivals.reset_index()
inbound_2 = inbound_2[inbound_2['Indicators'] != 'Total arrivals']
inbound_2 = inbound_2.groupby('Countries').sum()[np.arange(1995,2020)].reset_index()
inbound_2 = inbound_2.set_index('Countries')
inbound_2

inbound = inbound_arrivals.reset_index()
#Selecting 'Total arrivals'
inbound = inbound[inbound['Indicators'] == 'Total arrivals']
inbound = inbound.drop(['Indicators', 'Units', 2020], axis = 1)
inbound = inbound.set_index('Countries')
#Replacing NaN data of inbound with values from inbound_2
inbound = inbound.combine_first(inbound_2).reset_index()
#Changing the units from thounsands to millions
inbound[inbound.select_dtypes(include = ['number']).columns] /= 1000.0
inbound.insert(0, 'Units', 'Millions')
#Setting all 0 to NaN
inbound = inbound.replace({0: np.nan})
#Forward filling before backward filling
inbound[np.arange(1995,2020)] = inbound[np.arange(1995,2020)].ffill(axis = 1).bfill(axis = 1)
#Summing the data
inbound['sum'] = inbound[np.arange(1995,2020)].sum(axis=1)
#Getting alpha 2 code
inbound['country_alpha_2'] = inbound.apply(lambda row: findCountry2(row.Countries) , axis = 1)
#Getting alpha 3 code
inbound['country_alpha_3'] = inbound.apply(lambda row: findCountry3(row.Countries) , axis = 1)
#Merging with countries to get latitude and longitude of each country
inbound = pd.merge(inbound, countries, left_on='country_alpha_2', right_on='country', how='left')
#Merging with region to get region of each country
inbound = pd.merge(inbound, region[['alpha-2', 'region']], left_on='country_alpha_2', right_on='alpha-2', how='left')
#Dropping redundant data
inbound = inbound.drop(['alpha-2', 'country', 'Countries'],axis=1)
#Rearranging the columns
cols = inbound.columns.tolist()
cols = [cols[-2]] + cols[-6:-4] + [cols[-1]] + cols[-4:-2] + cols[:-6]
inbound = inbound[cols]
#Dropping null data
inbound = inbound[inbound['name'].notna()]
#Renaming the column
inbound = inbound.rename(columns={'Units':'units'})
#Sorting through sum
inbound = inbound.sort_values(by='sum', ascending = False)
#Dropping duplicate data
inbound = inbound.drop_duplicates(subset = 'name')
#Resetting index
inbound =  inbound.reset_index(drop = True)
#Setting the alpha 2 code and alpha 3 code specifically for Namibia
inbound.loc[inbound['name'] == 'Namibia', 'country_alpha_2'] = 'NA'
inbound.loc[inbound['name'] == 'Namibia', 'country_alpha_3'] = 'NAM'
inbound


#Adding up 'Overnights visitors (tourists)' and 'Same-day visitors (excursionists)' to get 'Total trips'
domestic_2 = domestic_trips.reset_index()
domestic_2 = domestic_2[domestic_2['Indicators'] != 'Total trips']
domestic_2 = domestic_2.groupby('Countries').sum()[np.arange(1995,2020)].reset_index()
domestic_2 = domestic_2.set_index('Countries')
domestic_2

domestic = domestic_trips.reset_index()
#Selecting 'Total trips'
domestic = domestic[domestic['Indicators'] == 'Total trips']
domestic = domestic.drop(['Indicators', 'Units', 2020], axis = 1)
domestic = domestic.set_index('Countries')
#Replacing NaN data of domestic with values from domestic_2
domestic = domestic.combine_first(domestic_2).reset_index()
#Changing the units from thounsands to millions
domestic[domestic.select_dtypes(include = ['number']).columns] /= 1000.0
domestic.insert(0, 'Units', 'Millions')
#Setting all 0 to NaN
domestic = domestic.replace({0: np.nan})
#Forward filling before backward filling
domestic[np.arange(1995,2020)] = domestic[np.arange(1995,2020)].ffill(axis = 1).bfill(axis = 1)
#Summing the data
domestic['sum'] = domestic[np.arange(1995,2020)].sum(axis=1)
#Getting alpha 2 code
domestic['country_alpha_2'] = domestic.apply(lambda row: findCountry2(row.Countries) , axis = 1)
#Getting alpha 3 code
domestic['country_alpha_3'] = domestic.apply(lambda row: findCountry3(row.Countries) , axis = 1)
#Merging with countries to get latitude and longitude of each country
domestic = pd.merge(domestic, countries, left_on='country_alpha_2', right_on='country', how='left')
#Merging with region to get region of each country
domestic = pd.merge(domestic, region[['alpha-2', 'region']], left_on='country_alpha_2', right_on='alpha-2', how='left')
#Dropping redundant data
domestic = domestic.drop(['alpha-2', 'country', 'Countries'],axis=1)
#Rearranging the columns
cols = domestic.columns.tolist()
cols = [cols[-2]] + cols[-6:-4] + [cols[-1]] + cols[-4:-2] + cols[:-6]
domestic = domestic[cols]
#Dropping null data
domestic = domestic[domestic['name'].notna()]
#Renaming the column
domestic = domestic.rename(columns={'Units':'units'})
#Sorting through sum
domestic = domestic.sort_values(by='sum', ascending = False)
#Dropping duplicate data
domestic = domestic.drop_duplicates(subset = 'name')
#Resetting index
domestic =  domestic.reset_index(drop = True)
#Setting the alpha 2 code and alpha 3 code specifically for Namibia
domestic.loc[domestic['name'] == 'Namibia', 'country_alpha_2'] = 'NA'
domestic.loc[domestic['name'] == 'Namibia', 'country_alpha_3'] = 'NAM'
domestic


#Creating map
outbound_map = folium.Map()
#Adding choropleth map
folium.Choropleth(geo_data = 'https://github.com/simonepri/geo-maps/releases/download/v0.6.0/countries-land-10km.geo.json',
                  data = outbound,
                  columns = ['country_alpha_3', 'sum'],
                  key_on = 'feature.properties.A3',
                  fill_color = 'RdBu',
                  fill_opacity = 0.8,
                  line_opacity = 0.2,
                  legend_name = 'Total Number of Outbound Tourism from 1995 to 2019 in Millions'
                 ).add_to(outbound_map)
outbound_map


#Adding markers
for i in range(0,len(outbound)):
    folium.Marker(
        location = [outbound.iloc[i]['latitude'], outbound.iloc[i]['longitude']],
        popup = outbound.iloc[i]['name'] + '\n' + str(int(outbound.iloc[i]['sum'] * 1000000))
    ).add_to(outbound_map)
outbound_map


outbound_sum = outbound.copy()
#Setting name as index
outbound_sum = outbound_sum.set_index('name')
#Dropping redundant data
outbound_sum = outbound_sum[['sum']]
#Sorting data by sum
outbound_sum = outbound_sum.sort_values(by = 'sum', ascending = False)
#Dropping data <= 0
outbound_sum = outbound_sum[outbound_sum['sum'] > 0].T
#Multiplying by a million
outbound_sum *= 1000000
outbound_sum


#Plotting vertical bar graph and setting the x-axis to show the top 15 countries by default
outbound_vbar = px.bar(outbound_sum.T, title = "Countries' Total Number of Outbound Tourism from 1995 to 2019", labels = {'value': 'Total Number of Outbound Tourism', 'name': 'Country'}).for_each_trace(lambda t: t.update(name = {'sum': 'Total Number of Outbound Tourism'}[t.name])).update_layout(xaxis_rangeslider_visible=True, xaxis_range=[-0.5, 14.5]).update_yaxes(fixedrange = False)
outbound_vbar


#Plotting horizontal bar graph, reversing the order, and setting the y-axis to show the top 15 countries by default
outbound_hbar = px.bar(outbound_sum.T.sort_values(by = 'sum', ascending = True), title = "Countries' Total Number of Outbound Tourism from 1995 to 2019", labels = {'value': 'Total Number of Outbound Tourism', 'name': 'Country'}, orientation='h').for_each_trace(lambda t: t.update(name = {'sum': 'Total Number of Outbound Tourism'}[t.name])).update_layout(yaxis_range=[len(outbound_sum.columns)-15.5, len(outbound_sum.columns)-0.5])
outbound_hbar


#Creating map
inbound_map = folium.Map()
#Adding choropleth map
folium.Choropleth(geo_data = 'https://github.com/simonepri/geo-maps/releases/download/v0.6.0/countries-land-10km.geo.json',
                  data = inbound,
                  columns = ['country_alpha_3', 'sum'],
                  key_on = 'feature.properties.A3',
                  fill_color = 'RdBu',
                  fill_opacity = 0.8,
                  line_opacity = 0.2,
                  legend_name = 'Total Number of Inbound Tourism from 1995 to 2019 in Millions'
                 ).add_to(inbound_map)
inbound_map


#Adding markers
for i in range(0,len(inbound)):
    folium.Marker(
        location = [inbound.iloc[i]['latitude'], inbound.iloc[i]['longitude']],
        popup = inbound.iloc[i]['name'] + '\n' + str(int(inbound.iloc[i]['sum'] * 1000000))
    ).add_to(inbound_map)
inbound_map


inbound_sum = inbound.copy()
#Setting name as index
inbound_sum = inbound_sum.set_index('name')
#Dropping redundant data
inbound_sum = inbound_sum[['sum']]
#Sorting data by sum
inbound_sum = inbound_sum.sort_values(by = 'sum', ascending = False)
#Dropping data <= 0
inbound_sum = inbound_sum[inbound_sum['sum'] > 0].T
#Multiplying by a million
inbound_sum *= 1000000
inbound_sum


#Setting figure size and resolution of figure
plt.figure(figsize=(15,5), dpi=300)
#Plotting vertical bar graph
inbound_sum_plot = sns.barplot(data = inbound_sum.T.head(15).T, color = 'skyblue')
#Rotating the x-axis labels so that they do not overlap
inbound_sum_plot.set_xticklabels(inbound_sum_plot.get_xticklabels(), rotation=45, ha="right")
#Naming x-axis
inbound_sum_plot.set_xlabel('Country')
#Naming y-axis
inbound_sum_plot.set_ylabel('Total Number of Inbound Tourism from 1995 to 2019')
#Naming the figure
inbound_sum_plot.set_title('Top 15 Countries with Largest Total Number of Inbound Tourism from 1995 to 2019')

Text(0.5, 1.0, 'Top 15 Countries with Largest Total Number of Inbound Tourism from 1995 to 2019')


#Plotting vertical bar graph and setting the x-axis to show the top 15 countries by default
inbound_vbar = px.bar(inbound_sum.T, title = "Countries' Total Number of Inbound Tourism from 1995 to 2019", labels = {'value': 'Total Number of Inbound Tourism', 'name': 'Country'}).for_each_trace(lambda t: t.update(name = {'sum': 'Total Number of Inbound Tourism'}[t.name])).update_layout(xaxis_rangeslider_visible=True, xaxis_range=[-0.5, 14.5]).update_yaxes(fixedrange = False)
inbound_vbar


#Plotting horizontal bar graph, reversing the order, and setting the y-axis to show the top 15 countries by default
inbound_hbar = px.bar(inbound_sum.T.sort_values(by = 'sum', ascending = True), title = "Countries' Total Number of Inbound Tourism from 1995 to 2019", labels = {'value': 'Total Number of Inbound Tourism', 'name': 'Country'}, orientation='h').for_each_trace(lambda t: t.update(name = {'sum': 'Total Number of Inbound Tourism'}[t.name])).update_layout(yaxis_range=[len(inbound_sum.columns)-15.5, len(inbound_sum.columns)-0.5])
inbound_hbar


#Creating map
domestic_map = folium.Map()
#Adding choropleth map
folium.Choropleth(geo_data = 'https://github.com/simonepri/geo-maps/releases/download/v0.6.0/countries-land-10km.geo.json',
                  data = domestic,
                  columns = ['country_alpha_3', 'sum'],
                  key_on = 'feature.properties.A3',
                  fill_color = 'RdBu',
                  fill_opacity = 0.8,
                  line_opacity = 0.2,
                  legend_name = 'Total Number of Domestic Tourism from 1995 to 2019 in Millions'
                 ).add_to(domestic_map)
domestic_map


#Adding markers
for i in range(0,len(domestic)):
    folium.Marker(
        location = [domestic.iloc[i]['latitude'], domestic.iloc[i]['longitude']],
        popup = domestic.iloc[i]['name'] + '\n' + str(int(domestic.iloc[i]['sum'] * 1000000))
    ).add_to(domestic_map)
domestic_map


domestic_sum = domestic.copy()
#Setting name as index
domestic_sum = domestic_sum.set_index('name')
#Dropping redundant data
domestic_sum = domestic_sum[['sum']]
#Sorting data by sum
domestic_sum = domestic_sum.sort_values(by = 'sum', ascending = False)
#Dropping data <= 0
domestic_sum = domestic_sum[domestic_sum['sum'] > 0].T
#Multiplying by a million
domestic_sum *= 1000000
domestic_sum


#Plotting vertical bar graph and setting the x-axis to show the top 15 countries by default
domestic_vbar = px.bar(domestic_sum.T, title = "Countries' Total Number of Domestic Tourism from 1995 to 2019", labels = {'value': 'Total Number of Domestic Tourism', 'name': 'Country'}).for_each_trace(lambda t: t.update(name = {'sum': 'Total Number of Domestic Tourism'}[t.name])).update_layout(xaxis_rangeslider_visible=True, xaxis_range=[-0.5, 14.5]).update_yaxes(fixedrange = False)
domestic_vbar


#Plotting horizontal bar graph, reversing the order, and setting the y-axis to show the top 15 countries by default
domestic_hbar = px.bar(domestic_sum.T.sort_values(by = 'sum', ascending = True), title = "Countries' Total Number of Domestic Tourism from 1995 to 2019", labels = {'value': 'Total Number of Domestic Tourism', 'name': 'Country'}, orientation='h').for_each_trace(lambda t: t.update(name = {'sum': 'Total Number of Domestic Tourism'}[t.name])).update_layout(yaxis_range=[len(domestic_sum.columns)-15.5, len(domestic_sum.columns)-0.5])
domestic_hbar


total_arrivals = inbound.copy()
#Dropping redundant data
total_arrivals = total_arrivals[['name', 'country_alpha_2', 'country_alpha_3', 'region', 'latitude', 'longitude', 'units', 'sum']]
#Renaming column
total_arrivals = total_arrivals.rename(columns = {'sum': 'inbound'})
#Merging
total_arrivals = pd.merge(total_arrivals, domestic[['name', 'sum']], on = 'name')
#Renaming column
total_arrivals = total_arrivals.rename(columns = {'sum': 'domestic'})
#Summing the total number of arrivals
total_arrivals['total_arrivals'] = total_arrivals[['inbound', 'domestic']].sum(axis = 1)
#Sorting the data by total number of arrivals
total_arrivals = total_arrivals.sort_values(by = 'total_arrivals', ascending = False).reset_index(drop = True)
total_arrivals


#Creating map
arrivals_map = folium.Map()
#Adding choropleth map
folium.Choropleth(geo_data = 'https://github.com/simonepri/geo-maps/releases/download/v0.6.0/countries-land-10km.geo.json',
                  data = total_arrivals,
                  columns = ['country_alpha_3', 'total_arrivals'],
                  key_on = 'feature.properties.A3',
                  fill_color = 'RdBu',
                  fill_opacity = 0.8,
                  line_opacity = 0.2,
                  legend_name = 'Total Number of Arrivals from 1995 to 2019 in Millions'
                 ).add_to(arrivals_map)
arrivals_map


#Adding markers
for i in range(0,len(total_arrivals)):
    folium.Marker(
        location = [total_arrivals.iloc[i]['latitude'], total_arrivals.iloc[i]['longitude']],
        popup = total_arrivals.iloc[i]['name'] + '\n' + str(int(total_arrivals.iloc[i]['total_arrivals'] * 1000000))
    ).add_to(arrivals_map)
arrivals_map


#Dropping redundant data
arrivals_sum = total_arrivals[['name', 'total_arrivals']]
#Setting name as index
arrivals_sum = arrivals_sum.set_index('name')
#Multiplying by a million
arrivals_sum *= 1000000
#Dropping data <= 0
arrivals_sum = arrivals_sum[arrivals_sum['total_arrivals'] > 0]
arrivals_sum


#Plotting vertical bar graph and setting the x-axis to show the top 15 countries by default
px.bar(arrivals_sum, title = 'Total Number of Arrivals from 1995 to 2019', labels = {'value': 'Total Number of Arrivals', 'name': 'Country'}).for_each_trace(lambda t: t.update(name = {'total_arrivals': 'Total Number of Arrivals'}[t.name])).update_layout(xaxis_range=[-0.5, 14.5])


#Plotting horizontal bar graph, reversing the order, and setting the y-axis to show the top 15 countries by default
arrivals_bar = px.bar(arrivals_sum.sort_values(by = 'total_arrivals', ascending = True), title = 'Total Number of Arrivals from 1995 to 2019', labels = {'value': 'Total Number of Arrivals', 'name': 'Country'}, orientation='h').for_each_trace(lambda t: t.update(name = {'total_arrivals': 'Total Number of Arrivals'}[t.name])).update_layout(yaxis_range=[len(arrivals_sum.index)-15.5, len(arrivals_sum.index)-0.5])
arrivals_bar


#Dropping redundant data
arrivals_stacked = total_arrivals[['name', 'inbound', 'domestic', 'total_arrivals']]
#Setting name and total_arrivals as the index
arrivals_stacked = arrivals_stacked.set_index(['name', 'total_arrivals'])
#Stack the data and renaming the columns
arrivals_stacked = arrivals_stacked.stack().to_frame().reset_index().rename(columns = {'level_2': 'type', 0: 'sum'})
#Dropping redundant data
arrivals_stacked = arrivals_stacked[['name', 'type', 'sum', 'total_arrivals']]
#Multiplying numerical data by a million
arrivals_stacked[arrivals_stacked.select_dtypes(include = ['number']).columns] *= 1000000
#Dropping data <= 0
arrivals_stacked = arrivals_stacked[arrivals_stacked['total_arrivals'] > 0]
arrivals_stacked


#Plotting horizontal stacked bar graph, reversing the order, and setting the y-axis to show the top 15 countries by default
arrivals_stacked_bar = px.bar(arrivals_stacked.sort_values(by = 'total_arrivals', ascending = True), x = 'sum', y = 'name', color = 'type', title = 'Total Number of Arrivals from 1995 to 2019', labels = {'sum': 'Total Number of Arrivals', 'name': 'Country'}, orientation = 'h').update_layout(yaxis_range=[len(arrivals_stacked.index)/2.0-15.5, len(arrivals_stacked.index)/2.0-0.5])
arrivals_stacked_bar


outbound_region = outbound.copy()
#Setting name as the index
outbound_region = outbound_region.set_index('name')
#Dropping redundant data
outbound_region = outbound_region[['region', 'sum']]
#Sorting data by sum
outbound_region = outbound_region.sort_values(by = 'sum', ascending = False)
#Dropping data <= 0
outbound_region = outbound_region[outbound_region['sum'] > 0]
#Multiplying numerical data by a million
outbound_region[outbound_region.select_dtypes(include=['number']).columns] *= 1000000
#Resetting the index
outbound_region = outbound_region.reset_index()
outbound_region


#Plotting treemap
outbound_tree = px.treemap(outbound_region, path=[px.Constant('World'), 'region', 'name'], values='sum', color='sum', color_continuous_scale='viridis', title = 'Total Number of Outbound Tourism from 1995 to 2019', width = 800, height = 800).update_layout(coloraxis_colorbar=dict(title = 'Total Number of Outbound Tourism'))
outbound_tree


inbound_region = inbound.copy()
#Setting name as the index
inbound_region = inbound_region.set_index('name')
#Dropping redundant data
inbound_region = inbound_region[['region', 'sum']]
#Sorting data by sum
inbound_region = inbound_region.sort_values(by = 'sum', ascending = False)
#Dropping data <= 0
inbound_region = inbound_region[inbound_region['sum'] > 0]
#Multiplying numerical data by a million
inbound_region[inbound_region.select_dtypes(include=['number']).columns] *= 1000000
#Resetting the index
inbound_region = inbound_region.reset_index()
inbound_region


#Plotting treemap
inbound_tree = px.treemap(inbound_region, path=[px.Constant('World'), 'region', 'name'], values='sum', color='sum', color_continuous_scale='viridis', title = 'Total Number of Inbound Tourism from 1995 to 2019', width = 800, height = 800).update_layout(coloraxis_colorbar=dict(title = 'Total Number of Inbound Tourism'))
inbound_tree


domestic_region = domestic.copy()
#Setting name as the index
domestic_region = domestic_region.set_index('name')
#Dropping redundant data
domestic_region = domestic_region[['region', 'sum']]
#Sorting data by sum
domestic_region = domestic_region.sort_values(by = 'sum', ascending = False)
#Dropping data <= 0
domestic_region = domestic_region[domestic_region['sum'] > 0]
#Multiplying numerical data by a million
domestic_region[domestic_region.select_dtypes(include=['number']).columns] *= 1000000
#Resetting the index
domestic_region = domestic_region.reset_index()
domestic_region


#Plotting treemap
domestic_tree = px.treemap(domestic_region, path=[px.Constant('World'), 'region', 'name'], values='sum', color='sum', color_continuous_scale='viridis', title = 'Total Number of Domestic Tourism from 1995 to 2019', width = 800, height = 800).update_layout(coloraxis_colorbar=dict(title = 'Total Number of Domestic Tourism'))
domestic_tree


arrivals_region = total_arrivals.copy()
#Setting name as the index
arrivals_region = arrivals_region.set_index('name')
#Dropping redundant data
arrivals_region = arrivals_region[['region', 'total_arrivals']]
#Sorting data by total_arrivals
arrivals_region = arrivals_region.sort_values(by = 'total_arrivals', ascending = False)
#Dropping data <= 0
arrivals_region = arrivals_region[arrivals_region['total_arrivals'] > 0]
#Multiplying numerical data by a million
arrivals_region[arrivals_region.select_dtypes(include=['number']).columns] *= 1000000
#Resetting the index
arrivals_region = arrivals_region.reset_index()
arrivals_region


#Plotting treemap
arrivals_tree = px.treemap(arrivals_region, path=[px.Constant('World'), 'region', 'name'], values='total_arrivals', color='total_arrivals', color_continuous_scale='RdBu', title = 'Total Number of Arrivals from 1995 to 2019', width = 800, height = 800).update_layout(coloraxis_colorbar=dict(title = 'Total Number of Arrivals'))
arrivals_tree


total = outbound.copy()
#Dropping redundant data
total = total[['name', 'country_alpha_2', 'country_alpha_3', 'region', 'latitude', 'longitude', 'units', 'sum']]
#Renaming column
total = total.rename(columns = {'sum': 'outbound'})
#Merging
total = pd.merge(total, inbound[['name', 'sum']], on = 'name')
#Renaming column
total = total.rename(columns = {'sum': 'inbound'})
#Merging
total = pd.merge(total, domestic[['name', 'sum']], on = 'name')
#Renaming column
total = total.rename(columns = {'sum': 'domestic'})
#Summing the total number of tourism
total['total'] = total[['outbound', 'inbound', 'domestic']].sum(axis = 1)
#Sorting the data by total number of tourism
total = total.sort_values(by = 'total', ascending = False).reset_index(drop = True)
total


total_region = total.copy()
#Setting name as the index
total_region = total_region.set_index('name')
#Dropping redundant data
total_region = total_region[['region', 'total']]
#Sorting data by total
total_region = total_region.sort_values(by = 'total', ascending = False)
#Dropping data <= 0
total_region = total_region[total_region['total'] > 0]
#Multiplying numerical data by a million
total_region[total_region.select_dtypes(include=['number']).columns] *= 1000000
#Resetting the index
total_region = total_region.reset_index()
total_region


#Plotting treemap
total_tree = px.treemap(total_region, path=[px.Constant('World'), 'region', 'name'], values='total', color='total', color_continuous_scale='RdBu', title = 'Total Number of Tourism from 1995 to 2019', width = 800, height = 800).update_layout(coloraxis_colorbar=dict(title = 'Total Number of Tourism'))
total_tree


#Plotting grouped bar graph
px.bar(total_region, x = 'name', y = 'total', color = 'region', title = 'Total Number of Tourism in Each Region', labels = {'total': 'Total Number of Tourism', 'name': 'Country'})


#Plotting vertical grouped bar graph using only the top 5 countries of each region
px.bar(total_region.groupby('region').head(5), x = 'name', y = 'total', color = 'region', title = 'Top 5 Countries with Highest Total Number of Tourism in Each Region', labels = {'total': 'Total Number of Tourism', 'name': 'Country'})


#Plotting horizontal grouped bar graph using only the top 3 countries of each region and reversing the order
total_group = px.bar(total_region.groupby('region').head(3), x = 'total', y = 'name', color = 'region', title = 'Top 3 Countries with Highest Total Number of Tourism in Each Region', labels = {'total': 'Total Number of Tourism', 'name': 'Country'}, orientation = 'h').update_layout(yaxis = dict(autorange = 'reversed'))
total_group


#Plotting side-by-side boxplot with categorical scatterplot at the side using only the top 5 countries of each region
total_box = px.box(total_region.groupby('region').head(5), y = 'total', x = 'region', color = 'region', hover_data = total_region.columns, points = 'all', title = 'Boxplot of Top 5 Countries with Highest Total Number of Tourism in Each Region', labels = {'total': 'Total Number of Tourism', 'name': 'Country'})
total_box


#Plotting side-by-side violinplot
plt.figure(figsize=(15,10))
sns.violinplot(data = total_region, y = total_region['total'], x = total_region['region'], inner = 'quartile')
plt.show()


#Plotting side-by-side violinplot with categorical scatterplot at the side using only the top 5 countries of each region
total_violin = px.violin(total_region.groupby('region').head(5), y = 'total', x = 'region', color = 'region', box=True, points = 'all', hover_data = total_region.columns, title = 'Violinplot of Top 5 Countries with Highest Total Number of Tourism in Each Region', labels = {'total': 'Total Number of Tourism', 'name': 'Country'})
total_violin


#Creating map
total_map = folium.Map()
#Adding choropleth map
folium.Choropleth(geo_data = 'https://github.com/simonepri/geo-maps/releases/download/v0.6.0/countries-land-10km.geo.json',
                  data = total,
                  columns = ['country_alpha_3', 'total'],
                  key_on = 'feature.properties.A3',
                  fill_color = 'RdBu',
                  fill_opacity = 0.8,
                  line_opacity = 0.2,
                  legend_name = 'Total Number of Tourism from 1995 to 2019 in Millions'
                 ).add_to(total_map)
total_map


#Adding markers
for i in range(0,len(total)):
    folium.Marker(
        location = [total.iloc[i]['latitude'], total.iloc[i]['longitude']],
        popup = total.iloc[i]['name'] + '\n' + str(int(total.iloc[i]['total'] * 1000000))
    ).add_to(total_map)
total_map


#Dropping redundant data
tourism_total = total[['name', 'total']]
#Setting name as index
tourism_total = tourism_total.set_index('name')
#Multiplying by a million
tourism_total *= 1000000
#Dropping data <= 0
tourism_total = tourism_total[tourism_total['total'] > 0]
tourism_total


#Plotting vertical bar graph and setting the x-axis to show the top 15 countries by default
px.bar(tourism_total, title = 'Total Number of Tourism from 1995 to 2019', labels = {'value': 'Total Number of Tourism', 'name': 'Country'}).for_each_trace(lambda t: t.update(name = {'total': 'Total Number of Tourism'}[t.name])).update_layout(xaxis_range=[-0.5, 14.5])


#Plotting horizontal bar graph, reversing the order, and setting the y-axis to show the top 15 countries by default
total_bar = px.bar(tourism_total.sort_values(by = 'total', ascending = True), title = 'Total Number of Tourism from 1995 to 2019', labels = {'value': 'Total Number of Tourism', 'name': 'Country'}, orientation='h').for_each_trace(lambda t: t.update(name = {'total': 'Total Number of Tourism'}[t.name])).update_layout(yaxis_range=[len(tourism_total.index)-15.5, len(tourism_total.index)-0.5])
total_bar


#Dropping redundant data
total_stacked = total[['name', 'outbound', 'inbound', 'domestic', 'total']]
#Setting name and total_arrivals as the index
total_stacked = total_stacked.set_index(['name', 'total'])
#Stack the data and renaming the columns
total_stacked = total_stacked.stack().to_frame().reset_index().rename(columns = {'level_2': 'type', 0: 'sum'})
#Dropping redundant data
total_stacked = total_stacked[['name', 'type', 'sum', 'total']]
#Multiplying numerical data by a million
total_stacked[total_stacked.select_dtypes(include = ['number']).columns] *= 1000000
#Dropping data <= 0
total_stacked = total_stacked[total_stacked['total'] > 0]
total_stacked


#Plotting vertical stacked bar graph and setting the x-axis to show the top 15 countries by default
px.bar(total_stacked, x = 'name', y = 'sum', color = 'type', title = 'Total Number of Tourism from 1995 to 2019', labels = {'value': 'Total Number of Tourism', 'name': 'Country'}).update_layout(xaxis_range=[-0.5, 14.5])


#Plotting vertical bar graph, setting an x-axis rangeslider, and setting the x-axis to show the top 15 countries by default
total_stacked_vbar = px.bar(total_stacked, x = 'name', y = 'sum', color = 'type', title = 'Total Number of Tourism from 1995 to 2019', labels = {'sum': 'Total Number of Tourism', 'name': 'Country'}).update_layout(xaxis_rangeslider_visible=True, xaxis_range=[-0.5, 14.5]).update_yaxes(fixedrange = False)
total_stacked_vbar


#Plotting horizontal stacked bar graph, reversing the order, and setting the y-axis to show the top 15 countries by default
total_stacked_hbar = px.bar(total_stacked.sort_values(by = 'total', ascending = True), x = 'sum', y = 'name', color = 'type', title = 'Total Number of Tourism from 1995 to 2019', labels = {'sum': 'Total Number of Tourism', 'name': 'Country'}, orientation = 'h').update_layout(yaxis_range=[len(total_stacked.index)/3.0-15.5, len(total_stacked.index)/3.0-0.5])
total_stacked_hbar


outbound_year = outbound.copy()
outbound_year = outbound_year.drop(['country_alpha_2','country_alpha_3','latitude','longitude','units'], axis = 1)
outbound_year = outbound_year.set_index(['name', 'region'])
outbound_year = outbound_year[np.arange(1995,2020)].stack().to_frame().reset_index()
outbound_year = outbound_year.rename(columns = {'level_2': 'year', 0: 'sum'})
outbound_year['sum'] *= 1000000
outbound_year


top_outbound = outbound.nlargest(10, 'sum')
top_outbound = top_outbound.set_index('name')
top_outbound = top_outbound.drop(['country_alpha_2', 'country_alpha_3', 'region', 'latitude', 'longitude', 'units', 'sum'],axis=1)
top_outbound.columns.name = 'year'
top_outbound = top_outbound.T
top_outbound[top_outbound.select_dtypes(include=['number']).columns] *= 1000000
top_outbound


#Plotting line graph
outbound_growth = px.line(top_outbound, title = 'Number of Outbound Tourism of the Top 10 Countries over the Years', labels = {'value': 'Number of Outbound Tourism', 'year': 'Year'}, markers = True).update_layout(legend_title = 'Countries')
outbound_growth


inbound_year = inbound.copy()
inbound_year = inbound_year.drop(['country_alpha_2','country_alpha_3','latitude','longitude','units'], axis = 1)
inbound_year = inbound_year.set_index(['name', 'region'])
inbound_year = inbound_year[np.arange(1995,2020)].stack().to_frame().reset_index()
inbound_year = inbound_year.rename(columns = {'level_2': 'year', 0: 'sum'})
inbound_year['sum'] *= 1000000
inbound_year


#Plotting line graph
px.line(inbound_year, x = 'year', y = 'sum', color='region', line_group='name', title = 'Total Number of Inbound Tourism from 1995 to 2019', labels = {'sum': 'Number of Inbound Tourism', 'year': 'Year'}, markers = True).update_layout(legend_title = 'Region')


#Plotting area graph
px.area(inbound_year, x = 'year', y = 'sum', color='region', line_group='name', title = 'Total Number of Inbound Tourism from 1995 to 2019', labels = {'sum': 'Number of Inbound Tourism', 'year': 'Year'}).update_layout(legend_title = 'Region')


top_inbound = inbound.nlargest(10, 'sum')
top_inbound = top_inbound.set_index('name')
top_inbound = top_inbound.drop(['country_alpha_2', 'country_alpha_3', 'region', 'latitude', 'longitude', 'units', 'sum'],axis=1)
top_inbound.columns.name = 'year'
top_inbound = top_inbound.T
top_inbound[top_inbound.select_dtypes(include=['number']).columns] *= 1000000
top_inbound


plt.figure(figsize=(15,5), dpi=300)
sns.lineplot(data = top_inbound, dashes = False)
plt.legend(bbox_to_anchor=(1.01, 1.05))
plt.title('Number of Inbound Tourism of the Top 10 Countries over the Years')
plt.xlabel('Year')
plt.ylabel('Number of Inbound Tourism')
plt.show()


#Plotting line graph
inbound_growth = px.line(top_inbound, title = 'Number of Inbound Tourism of the Top 10 Countries over the Years', labels = {'value': 'Number of Inbound Tourism', 'year': 'Year'}, markers = True).update_layout(legend_title = 'Countries')
inbound_growth


domestic_year = domestic.copy()
domestic_year = domestic_year.drop(['country_alpha_2','country_alpha_3','latitude','longitude','units'], axis = 1)
domestic_year = domestic_year.set_index(['name', 'region'])
domestic_year = domestic_year[np.arange(1995,2020)].stack().to_frame().reset_index()
domestic_year = domestic_year.rename(columns = {'level_2': 'year', 0: 'sum'})
domestic_year['sum'] *= 1000000
domestic_year


top_domestic = domestic.nlargest(10, 'sum')
top_domestic = top_domestic.set_index('name')
top_domestic = top_domestic.drop(['country_alpha_2', 'country_alpha_3', 'region', 'latitude', 'longitude', 'units', 'sum'],axis=1)
top_domestic.columns.name = 'year'
top_domestic = top_domestic.T
top_domestic[top_domestic.select_dtypes(include=['number']).columns] *= 1000000
top_domestic


#Plotting line graph
domestic_growth = px.line(top_domestic, title = 'Number of Domestic Tourism of the Top 10 Countries over the Years', labels = {'value': 'Number of Domestic Tourism', 'year': 'Year'}, markers = True).update_layout(legend_title = 'Countries')
domestic_growth


inbound_19 = inbound[['name',2019]].dropna().sort_values(by = 2019, ascending = False).reset_index(drop = True).reset_index().drop(2019, axis = 1)
inbound_19 = inbound_19.rename(columns = {'index': 'Inbound Tourism'})
inbound_19['Inbound Tourism'] += 1
inbound_19 = pd.merge(ranking_19, inbound_19, left_on = 'Country', right_on = 'name', how = 'inner').drop('name', axis = 1)
inbound_19


inbound_ranking = sns.pairplot(inbound_19, y_vars=['Inbound Tourism']).fig


sns.regplot(data = inbound_19, x = 'Heritage', y = 'Inbound Tourism')
plt.show()


sns.jointplot(data = inbound_19, x = 'Heritage', y = 'Inbound Tourism')
plt.show()


sns.jointplot(data = inbound_19, x = 'Heritage', y = 'Inbound Tourism', kind = 'hex')
plt.show()


sns.jointplot(data = inbound_19, x = 'Heritage', y = 'Inbound Tourism', kind = 'kde')
plt.show()


inbound_heritage_contour = px.density_contour(inbound_19, x = 'Heritage', y = 'Inbound Tourism', title = '2D Histogram Contour Plot between the Rankings for Inbound Tourism and Heritage of Countries in 2019').update_traces(contours_coloring="fill", contours_showlabels = True)
inbound_heritage_contour


inbound_heritage = px.scatter(inbound_19, x = 'Heritage', y = 'Inbound Tourism', trendline='ols', trendline_color_override='darkblue', title = 'The Correlation between the Rankings for Inbound Tourism and Heritage of Countries in 2019')
inbound_heritage


heritage_coef, heritage_value = stats.pearsonr(inbound_19['Heritage'], inbound_19['Inbound Tourism'])
heritage_coef, heritage_value

(0.6676240739225271, 1.1103724933546565e-10)


inbound_culture_contour = px.density_contour(inbound_19, x = 'Cultural Influence', y = 'Inbound Tourism', title = '2D Histogram Contour Plot between the Rankings for Inbound Tourism and Cultural Influence of Countries in 2019').update_traces(contours_coloring="fill", contours_showlabels = True)
inbound_culture_contour


inbound_culture = px.scatter(inbound_19, x = 'Cultural Influence', y = 'Inbound Tourism', trendline='ols', trendline_color_override='darkblue', title = 'The Correlation between the Rankings for Inbound Tourism and Cultural Influence of Countries in 2019')
inbound_culture


culture_coef, culture_value = stats.pearsonr(inbound_19['Cultural Influence'], inbound_19['Inbound Tourism'])
culture_coef, culture_value

(0.4942019692089541, 8.846681908836526e-06)


lm = LinearRegression()
X_train, X_test, y_train, y_test = train_test_split(inbound_19[['Heritage']], inbound_19['Inbound Tourism'], test_size=0.2, random_state=0)
lm.fit(X_train, y_train)
yhat = lm.predict(X_test)
yhat
sns.kdeplot(y_test, color='r', label='Actual Value')
sns.kdeplot(yhat,  color='b', label='Fitted Value')
plt.legend()

<matplotlib.legend.Legend at 0x1e9dead3970>


lm.score(X_train, y_train)

0.44387460785374466


mlm = LinearRegression()
X_train2, X_test2, y_train2, y_test2 = train_test_split(inbound_19[['Entrepreneurship','Adventure','Citizenship','Cultural Influence','Heritage','Movers','Open for Business','Power','Quality of Life']], inbound_19['Inbound Tourism'], test_size=0.2, random_state=0)
mlm.fit(X_train2, y_train2)
yhat2 = mlm.predict(X_test2)

sns.kdeplot(y_test2, color='r', label='Actual Value')
sns.kdeplot(yhat2,  color='b', label='Fitted Value')
plt.legend()

<matplotlib.legend.Legend at 0x1e9de7c9a60>


mlm.score(X_train2, y_train2)

0.5532718300044949


year = countries_interest.reset_index()
year.Date = year.Date.astype('string').str[:4].astype('int')
year = year.groupby('Date').sum()
year = year.loc[np.arange(2004,2020)]
year = year.T.reset_index()
year.columns.name = ''
year[np.arange(2004,2020)] = year[np.arange(2004,2020)].div(year[np.arange(2004,2020)].max(axis = 1),axis = 0) * 100
year


np.arange(2004,2020).tolist().append(1)


inbound_interest = inbound.copy()
inbound_interest[np.arange(2004,2020)] = inbound_interest[np.arange(2004,2020)].div(inbound_interest[np.arange(2004,2020)].max(axis=1), axis=0) * 100
inbound_interest = inbound_interest.drop(['country_alpha_2', 'country_alpha_3', 'region', 'latitude', 'longitude', 'units', 'sum', 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003], axis = 1)
inbound_interest = inbound_interest.dropna()
inbound_interest


nrow = 40
ncol = 5

interest = plt.figure(figsize = (15,80))
gs = interest.add_gridspec(nrow, ncol, hspace = 0.5, wspace = 0)
axes = gs.subplots(sharex = True, sharey = True)

count=0
for r in range(nrow):
    for c in range(ncol):
        inbound_interest.set_index('name').iloc[count].plot(title = inbound_interest.set_index('name').iloc[count].name, ax = axes[r,c], ylim = (0,100))
        try:
            year.set_index('index').loc[inbound_interest.set_index('name').iloc[count].name].plot(title = inbound_interest.set_index('name').iloc[count].name, ax = axes[r,c], ylim = (0,100))
        except:
            pass
        count += 1

plt.show()


inbound_interest[inbound_interest.name == 'France'][np.arange(2004,2020)].T.rename(columns = {0: 'inbound tourism'}).plot()
year[year['index'] == 'France'].drop('index', axis= 1).T.rename(columns = {70: 'interest over time'}).plot()

<AxesSubplot:>


france_interest = pd.merge(inbound_interest[inbound_interest.name == 'France'][np.arange(2004,2020)].T.rename(columns = {0: 'inbound tourism'}), year[year['index'] == 'France'].drop('index', axis= 1).T.rename(columns = {70: 'interest over time'}), left_index=True, right_index=True)
france_interest


inbound_interest[inbound_interest.name == 'China'][np.arange(2004,2020)].T.rename(columns = {2: 'inbound tourism'}).plot()
year[year['index'] == 'China'].drop('index', axis= 1).T.rename(columns = {39: 'interest over time'}).plot()

<AxesSubplot:>


france_interest_over_time = px.line(france_interest, title = 'Percentage of Inbound Tourism and Interest Over Time of France', labels = {'value': 'Percentage', 'index': 'Year'}, markers = True)
france_interest_over_time


albania_interest = pd.merge(inbound_interest[inbound_interest.name == 'Albania'][np.arange(2004,2020)].T.rename(columns = {79: 'inbound tourism'}), year[year['index'] == 'Albania'].drop('index', axis= 1).T.rename(columns = {2: 'interest over time'}), left_index=True, right_index=True)
albania_interest


albania_interest_over_time = px.line(albania_interest, title = 'Percentage of Inbound Tourism and Interest Over Time of Albania', labels = {'value': 'Percentage', 'index': 'Year'}, markers = True)
albania_interest_over_time


china_interest = pd.merge(inbound_interest[inbound_interest.name == 'China'][np.arange(2004,2020)].T.rename(columns = {2: 'inbound tourism'}), year[year['index'] == 'China'].drop('index', axis= 1).T.rename(columns = {39: 'interest over time'}), left_index=True, right_index=True)
china_interest


china_interest_over_time = px.line(china_interest, title = 'Percentage of Inbound Tourism and Interest Over Time of China', labels = {'value': 'Percentage', 'index': 'Year'}, markers = True)
china_interest_over_time


trend_area = inbound[['name', 'region', 'country_alpha_3', 2019]].dropna().sort_values(by = 2019, ascending = False).reset_index(drop = True)
trend_area[2019] *= 1000000
trend_area = pd.merge(trend_area, area[['Country Code', 2019.0]], left_on =  'country_alpha_3', right_on = 'Country Code')
trend_area = trend_area.rename(columns = {'2019_x': 'inbound', '2019.0_y': 'area'})
trend_area = trend_area[(trend_area['area'] < 3000000)]
trend_area


inbound_area = px.scatter(trend_area, x = 'area', y = 'inbound', color = 'region', opacity=0.8, trendline='ols', title = 'The Correlation between Inbound Tourism and Area', labels = {'inbound': 'Inbound Tourism', 'area': 'Area'}).update_traces(marker=dict(size=5, line=dict(width=1, color='DarkSlateGrey')), selector=dict(mode='markers')).update_layout(legend_title = 'Region')
inbound_area


inbound_area_europe = trend_area[trend_area['region'] == 'Europe'].copy()
inbound_area_europe


sns.residplot(x = inbound_area_europe['area'], y = inbound_area_europe['inbound'])
plt.show()


train_idx, test_idx = train_test_split(inbound_area_europe.index, test_size=.25, random_state=0)
inbound_area_europe['split'] = 'train'
inbound_area_europe.loc[test_idx, 'split'] = 'test'

X = inbound_area_europe[['area']]
X_train = inbound_area_europe.loc[train_idx, ['area']]
y_train = inbound_area_europe.loc[train_idx, 'inbound']

model = LinearRegression()
model.fit(X_train, y_train)
inbound_area_europe['prediction'] = model.predict(X)

inbound_area_europe['residual'] = inbound_area_europe['prediction'] - inbound_area_europe['inbound']

inbound_area_europe_residplot = px.scatter(
    inbound_area_europe, x='prediction', y='residual',
    marginal_y='violin',
    color='split', trendline='ols'
)
inbound_area_europe_residplot


europe_area_coef, europe_area_value = stats.pearsonr(trend_area['area'], trend_area['inbound'])
europe_area_coef, europe_area_value

(0.127905459662025, 0.0802483560283787)


outbound_map


outbound_vbar


outbound_hbar


inbound_map


inbound_vbar


inbound_hbar


domestic_map


domestic_vbar


domestic_hbar


arrivals_map


arrivals_bar


arrivals_stacked_bar


outbound_tree


inbound_tree


domestic_tree


arrivals_tree


total_tree


total_group


total_box


total_bar


total_stacked_vbar


total_stacked_hbar


outbound_growth


outbound_growth.update_traces({'line': {'color': 'lightgrey'}}).update_traces(patch = {'line': {'color': 'blue', 'width': 2}}, selector={'legendgroup': 'United States of America'}).add_annotation(ax = 2005, ay = 79215000 ,axref = "x", ayref='y', x = 2006, y = 148511000, text = 'Surge', showarrow=True, xshift = -30, yshift = 15, arrowhead = 4, arrowwidth = 2, font_size = 20)


inbound_growth


inbound_growth.update_traces({'line': {'color': 'lightgrey'}}).update_traces(patch = {'line': {'color': 'blue', 'width': 2}}, selector={'legendgroup': 'France'}).add_annotation(ax = 1997, ay = 157551000 ,axref = "x", ayref='y', x = 1998, y = 70109000, text = 'Drop', showarrow=True, xshift = 10, yshift = 15, arrowhead = 4, arrowwidth = 2, font_size = 20).add_annotation(ax = 2003, ay = 75048000 ,axref = "x", ayref='y', x = 2004, y = 190282000, text = 'Surge', showarrow=True, xshift = -30, yshift = 15, arrowhead = 4, arrowwidth = 2, font_size = 20)


domestic_growth


domestic_growth.update_traces({'line': {'color': 'lightgrey'}}).update_traces(patch = {'line': {'color': 'blue', 'width': 2}}, selector={'legendgroup': 'China'}).add_annotation(ax = 1997, ay = 644000000 ,axref = "x", ayref='y', x = 2019, y = 6005852000, text = 'Steady Increase', showarrow=True, xshift = -30, yshift = 15, arrowhead = 4, arrowwidth = 2, font_size = 20)


inbound_ranking


inbound_heritage_contour


inbound_heritage.add_annotation(x = 25, y = 120, text = 'Correlation Coefficient = ' + str(heritage_coef) + '<br>' + 'P-Value = ' +  str(heritage_value), showarrow = False, font_size = 20)


inbound_culture_contour


inbound_culture.add_annotation(x = 25, y = 110, text = 'Correlation Coefficient = ' + str(culture_coef) + '<br>' + 'P-Value = ' +  str(culture_value), showarrow = False, font_size = 20)


interest


france_interest_over_time


albania_interest_over_time


china_interest_over_time


inbound_area.add_annotation(x = 600000, y = 100000000, text = 'Europe Correlation Coefficient = ' + str(europe_area_coef) + '<br>' + 'Europe P-Value = ' +  str(europe_area_value), showarrow = False, font_size = 10)


inbound_area_europe_residplot

		Units	1995	1996	1997	1998	1999	2000	2001	2002	2003	...	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020
Countries	Indicators
AFGHANISTAN	Total arrivals	Thousands	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
	Overnights visitors (tourists)	Thousands	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
	Same-day visitors (excursionists)	Thousands	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
ALBANIA	Total arrivals	Thousands	304.0	287.0	119.0	184.0	371.0	317.0	354.0	470.0	557.0	...	2932.0	3514.0	3256.0	3673.0	4131.0	4736.0	5118.0	5927.0	6406.0	2658.0
ALBANIA	Overnights visitors (tourists)	Thousands	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	2469.0	3156.0	2857.0	3341.0	3784.0	4070.0	4643.0	5340.0	6128.0	2604.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
ZAMBIA	Overnights visitors (tourists)	Thousands	163.0	264.0	341.0	362.0	404.0	457.0	492.0	565.0	413.0	...	920.0	859.0	915.0	947.0	932.0	956.0	1009.0	1072.0	1266.0	502.0
ZAMBIA	Same-day visitors (excursionists)	Thousands	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
ZIMBABWE	Total arrivals	Thousands	1416.0	1597.0	1336.0	2090.0	2250.0	1967.0	2217.0	2041.0	2256.0	...	2423.0	1794.0	1833.0	1880.0	2057.0	2168.0	2423.0	2580.0	2294.0	639.0
	Overnights visitors (tourists)	Thousands	1363.0	1577.0	1281.0	1986.0	2101.0	1868.0	2068.0	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
	Same-day visitors (excursionists)	Thousands	53.0	20.0	55.0	104.0	149.0	99.0	149.0	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

	name	alpha-2	alpha-3	country-code	iso_3166-2	region	sub-region	intermediate-region	region-code	sub-region-code	intermediate-region-code
0	Afghanistan	AF	AFG	4	ISO 3166-2:AF	Asia	Southern Asia	NaN	142.0	34.0	NaN
1	Åland Islands	AX	ALA	248	ISO 3166-2:AX	Europe	Northern Europe	NaN	150.0	154.0	NaN
2	Albania	AL	ALB	8	ISO 3166-2:AL	Europe	Southern Europe	NaN	150.0	39.0	NaN
3	Algeria	DZ	DZA	12	ISO 3166-2:DZ	Africa	Northern Africa	NaN	2.0	15.0	NaN
4	American Samoa	AS	ASM	16	ISO 3166-2:AS	Oceania	Polynesia	NaN	9.0	61.0	NaN
...	...	...	...	...	...	...	...	...	...	...	...
244	Wallis and Futuna	WF	WLF	876	ISO 3166-2:WF	Oceania	Polynesia	NaN	9.0	61.0	NaN
245	Western Sahara	EH	ESH	732	ISO 3166-2:EH	Africa	Northern Africa	NaN	2.0	15.0	NaN
246	Yemen	YE	YEM	887	ISO 3166-2:YE	Asia	Western Asia	NaN	142.0	145.0	NaN
247	Zambia	ZM	ZMB	894	ISO 3166-2:ZM	Africa	Sub-Saharan Africa	Eastern Africa	2.0	202.0	14.0
248	Zimbabwe	ZW	ZWE	716	ISO 3166-2:ZW	Africa	Sub-Saharan Africa	Eastern Africa	2.0	202.0	14.0

	country	latitude	longitude	name
0	AD	42.546245	1.601554	Andorra
1	AE	23.424076	53.847818	United Arab Emirates
2	AF	33.939110	67.709953	Afghanistan
3	AG	17.060816	-61.796428	Antigua and Barbuda
4	AI	18.220554	-63.068615	Anguilla
...	...	...	...	...
240	YE	15.552727	48.516388	Yemen
241	YT	-12.827500	45.166244	Mayotte
242	ZA	-30.559482	22.937506	South Africa
243	ZM	-13.133897	27.849332	Zambia
244	ZW	-19.015438	29.154857	Zimbabwe

	Country Name	Country Code	1961.0	1962.0	1963.0	1964.0	1965.0	1966.0	1967.0	1968.0	...	2010.0	2011.0	2012.0	2013.0	2014.0	2015.0	2016.0	2017.0	2018.0	2019.0
0	Aruba	ABW	180.0	180.0	180.0	180.0	180.0	180.0	180.0	180.0	...	1.800000e+02	180.00	1.800000e+02	1.800000e+02	1.800000e+02	1.800000e+02	1.800000e+02	1.800000e+02	1.800000e+02	1.800000e+02
1	Africa Eastern and Southern	AFE	14571611.0	14571611.0	14571611.0	14571611.0	14571611.0	14571611.0	14571611.0	14571611.0	...	1.472096e+07	14721240.05	1.484517e+07	1.484513e+07	1.484509e+07	1.484514e+07	1.484515e+07	1.484514e+07	1.484515e+07	1.484516e+07
2	Afghanistan	AFG	652230.0	652230.0	652230.0	652230.0	652230.0	652230.0	652230.0	652230.0	...	6.522300e+05	652230.00	6.522300e+05	6.522300e+05	6.522300e+05	6.522300e+05	6.522300e+05	6.522300e+05	6.522300e+05	6.522300e+05
3	Africa Western and Central	AFW	9046580.0	9046580.0	9046580.0	9046580.0	9046580.0	9046580.0	9046580.0	9046580.0	...	9.045780e+06	9045780.00	9.045780e+06	9.045780e+06	9.045780e+06	9.045780e+06	9.045780e+06	9.045780e+06	9.045780e+06	9.045780e+06
4	Angola	AGO	1246700.0	1246700.0	1246700.0	1246700.0	1246700.0	1246700.0	1246700.0	1246700.0	...	1.246700e+06	1246700.00	1.246700e+06	1.246700e+06	1.246700e+06	1.246700e+06	1.246700e+06	1.246700e+06	1.246700e+06	1.246700e+06
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
261	Kosovo	XKX	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
262	Yemen, Rep.	YEM	527970.0	527970.0	527970.0	527970.0	527970.0	527970.0	527970.0	527970.0	...	5.279700e+05	527970.00	5.279700e+05	5.279700e+05	5.279700e+05	5.279700e+05	5.279700e+05	5.279700e+05	5.279700e+05	5.279700e+05
263	South Africa	ZAF	1213090.0	1213090.0	1213090.0	1213090.0	1213090.0	1213090.0	1213090.0	1213090.0	...	1.213090e+06	1213090.00	1.213090e+06	1.213090e+06	1.213090e+06	1.213090e+06	1.213090e+06	1.213090e+06	1.213090e+06	1.213090e+06
264	Zambia	ZMB	743390.0	743390.0	743390.0	743390.0	743390.0	743390.0	743390.0	743390.0	...	7.433900e+05	743390.00	7.433900e+05	7.433900e+05	7.433900e+05	7.433900e+05	7.433900e+05	7.433900e+05	7.433900e+05	7.433900e+05
265	Zimbabwe	ZWE	386850.0	386850.0	386850.0	386850.0	386850.0	386850.0	386850.0	386850.0	...	3.868500e+05	386850.00	3.868500e+05	3.868500e+05	3.868500e+05	3.868500e+05	3.868500e+05	3.868500e+05	3.868500e+05	3.868500e+05

	name	country_alpha_2	country_alpha_3	region	latitude	longitude	units	1995	1996	1997	...	2011	2012	2013	2014	2015	2016	2017	2018	2019	sum
0	United States of America	US	USA	Americas	37.090240	-95.712891	Millions	74.031	76.803	78.481	...	114.089	116.329	118.968	121.699	130.364	141.526	148.045	158.4454	170.9301	2781.9205
1	Mexico	MX	MEX	Americas	23.634501	-102.552784	Millions	103.161	103.442	107.242	...	88.113	87.332	90.787	90.982	94.988	97.372	94.274	86.2800	82.7520	2636.9450
2	Germany	DE	DEU	Europe	51.165691	10.451526	Millions	55.800	55.800	55.800	...	84.692	82.729	87.459	83.008	83.737	90.966	92.402	108.5420	99.5330	2048.5650
3	Namibia	NA	NAM	Africa	-22.957640	18.490410	Millions	47.594	47.594	47.594	...	84.816	85.276	84.414	84.519	89.082	91.758	91.304	92.2140	94.7150	1833.0990
4	United Kingdom	GB	GBR	Europe	55.378051	-3.435973	Millions	41.345	42.050	45.957	...	67.493	66.858	68.959	72.204	77.619	81.757	87.242	90.5710	93.0860	1642.6580
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
200	Jamaica	JM	JAM	Americas	18.109581	-77.297508	Millions	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	0.0000
201	Iraq	IQ	IRQ	Asia	33.223191	43.679291	Millions	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	0.0000
202	Haiti	HT	HTI	Americas	18.971187	-72.285215	Millions	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	0.0000
203	Guyana	GY	GUY	Americas	4.860416	-58.930180	Millions	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	0.0000
204	Lebanon	LB	LBN	Asia	33.854721	35.862285	Millions	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	0.0000

	Overall Rank	Country	Entrepreneurship	Adventure	Citizenship	Cultural Influence	Heritage	Movers	Open for Business	Power	Quality of Life
0	1	Switzerland	4	17	3	9	27	25	2	14	5
1	2	Japan	1	39	17	6	10	5	22	7	13
2	3	Canada	6	19	2	12	42	39	7	12	1
3	4	Germany	2	57	12	11	20	34	21	4	10
4	5	United Kingdom	5	40	11	5	12	53	23	5	12
...	...	...	...	...	...	...	...	...	...	...	...
70	71	Jordan	62	71	74	70	48	50	63	33	77
71	72	Tunisia	69	60	76	65	53	63	55	63	68
72	73	Belarus	56	61	50	71	67	66	76	35	67
73	74	Nigeria	67	74	77	63	76	57	58	46	74
74	75	Pakistan	68	77	78	79	71	56	72	22	73

	Afghanistan	Åland Islands	Albania	American Samoa	Andorra	Angola	Anguilla	Antarctica	Antigua and Barbuda	Argentina	...	Turks and Caicos Islands	Tuvalu	Uganda	Ukraine	United Arab Emirates	United Kingdom of Great Britain and Northern Ireland	United States of America	United States Minor Outlying Islands	Viet Nam	Zimbabwe
Date
2004-01-01	7	80	17	34	95	23	100	74	0	30	...	43	60	41	2	69	0	48	0	9	29
2004-02-01	7	0	19	29	83	27	68	86	44	30	...	100	100	42	2	73	0	53	0	11	28
2004-03-01	8	0	18	25	72	25	70	100	32	34	...	78	63	40	2	77	0	42	100	12	29
2004-04-01	8	0	20	28	49	27	61	81	24	34	...	28	58	43	2	75	0	45	80	13	31
2004-05-01	8	100	20	27	49	28	68	100	26	34	...	5	54	43	2	71	0	45	0	11	30
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
2022-03-01	9	24	37	16	34	30	54	62	37	43	...	18	39	91	89	34	55	15	11	20	26
2022-04-01	6	35	30	19	32	31	47	54	34	37	...	18	42	92	33	28	60	16	15	17	25
2022-05-01	6	37	39	18	29	33	40	52	33	37	...	15	39	89	22	28	61	16	13	20	29
2022-06-01	10	24	43	15	37	32	44	49	38	58	...	18	33	98	16	30	41	13	18	20	39
2022-07-01	5	25	45	17	37	35	44	49	32	39	...	17	38	100	13	27	38	12	16	19	46

	name	country_alpha_2	country_alpha_3	region	latitude	longitude	units	1995	1996	1997	...	2011	2012	2013	2014	2015	2016	2017	2018	2019	sum
0	France	FR	FRA	Europe	46.227638	2.213749	Millions	60.033	148.263	157.551	...	196.595000	197.522000	204.410000	206.599000	203.302000	203.042000	207.274000	211.998000	217.877	4001.252000
1	United States of America	US	USA	Americas	37.090240	-95.712891	Millions	79.732	82.756	82.525	...	147.271416	171.629897	179.309907	178.311354	176.864526	175.261488	174.291746	169.324918	165.478	3205.206252
2	China	CN	CHN	Asia	35.861660	104.195397	Millions	46.387	51.128	57.588	...	135.423000	132.405000	129.078000	128.499000	133.820000	141.774000	153.260000	158.606000	162.538	2805.217000
3	Mexico	MX	MEX	Americas	23.634501	-102.552784	Millions	85.446	90.394	92.915	...	75.732000	76.749000	78.100000	81.042000	87.129000	94.853000	99.349000	96.497000	97.406	2306.193000
4	Spain	ES	ESP	Europe	40.463667	-3.749220	Millions	52.460	55.077	62.415	...	99.187000	98.128000	103.231000	107.144000	109.834000	115.561000	121.717000	124.456000	126.170	2284.187000
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
200	Somalia	SO	SOM	Africa	5.152149	46.199616	Millions	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	0.000000
201	Equatorial Guinea	GQ	GNQ	Africa	1.650801	10.267895	Millions	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	0.000000
202	Nauru	NR	NRU	Oceania	-0.522778	166.931503	Millions	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	0.000000
203	Liberia	LR	LBR	Africa	6.428055	-9.429499	Millions	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	0.000000
204	Afghanistan	AF	AFG	Asia	33.939110	67.709953	Millions	NaN	NaN	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	0.000000

	total_arrivals
name
China	5.789407e+10
United States of America	5.454173e+10
India	1.894089e+10
United Kingdom	1.880950e+10
Japan	1.737805e+10
...	...
São Tomé and Príncipe	3.515000e+05
Montserrat	3.033050e+05
Marshall Islands	1.524000e+05
Niue	1.191000e+05
Tuvalu	3.870000e+04

	name	type	sum	total_arrivals
0	China	inbound	2.805217e+09	5.789407e+10
1	China	domestic	5.508885e+10	5.789407e+10
2	United States of America	inbound	3.205206e+09	5.454173e+10
3	United States of America	domestic	5.133652e+10	5.454173e+10
4	India	inbound	1.678710e+08	1.894089e+10
...	...	...	...	...
395	Marshall Islands	domestic	0.000000e+00	1.524000e+05
396	Niue	inbound	1.191000e+05	1.191000e+05
397	Niue	domestic	0.000000e+00	1.191000e+05
398	Tuvalu	inbound	3.870000e+04	3.870000e+04
399	Tuvalu	domestic	0.000000e+00	3.870000e+04

	name	region	sum
0	United States of America	Americas	2.781920e+09
1	Mexico	Americas	2.636945e+09
2	Germany	Europe	2.048565e+09
3	Namibia	Africa	1.833099e+09
4	United Kingdom	Europe	1.642658e+09
...	...	...	...
127	São Tomé and Príncipe	Africa	2.354000e+05
128	Palau	Oceania	2.250000e+05
129	Angola	Africa	7.500000e+04
130	Tuvalu	Oceania	6.050000e+04
131	Niue	Oceania	3.320000e+04

	name	region	sum
0	France	Europe	4.001252e+09
1	United States of America	Americas	3.205206e+09
2	China	Asia	2.805217e+09
3	Mexico	Americas	2.306193e+09
4	Spain	Europe	2.284187e+09
...	...	...	...
195	São Tomé and Príncipe	Africa	3.515000e+05
196	Montserrat	Americas	3.033050e+05
197	Marshall Islands	Oceania	1.524000e+05
198	Niue	Oceania	1.191000e+05
199	Tuvalu	Oceania	3.870000e+04

	name	region	total
0	China	Asia	5.935089e+10
1	United States of America	Americas	5.732365e+10
2	United Kingdom	Europe	2.045216e+10
3	India	Asia	1.922805e+10
4	Japan	Asia	1.780012e+10
...	...	...	...
195	Solomon Islands	Oceania	4.074000e+05
196	Montserrat	Americas	3.033050e+05
197	Marshall Islands	Oceania	1.524000e+05
198	Niue	Oceania	1.523000e+05
199	Tuvalu	Oceania	9.920000e+04

	name	type	sum	total
0	China	outbound	1.456823e+09	5.935089e+10
1	China	inbound	2.805217e+09	5.935089e+10
2	China	domestic	5.508885e+10	5.935089e+10
3	United States of America	outbound	2.781920e+09	5.732365e+10
4	United States of America	inbound	3.205206e+09	5.732365e+10
...	...	...	...	...
595	Niue	inbound	1.191000e+05	1.523000e+05
596	Niue	domestic	0.000000e+00	1.523000e+05
597	Tuvalu	outbound	6.050000e+04	9.920000e+04
598	Tuvalu	inbound	3.870000e+04	9.920000e+04
599	Tuvalu	domestic	0.000000e+00	9.920000e+04

name	United States of America	Mexico	Germany	Namibia	United Kingdom	China	Italy	Poland	Canada	Russia
year
1995	74031000.0	103161000.0	55800000.0	47594000.0	41345000.0	4520000.0	18173000.0	36387000.0	18206000.0	21329000.0
1996	76803000.0	103442000.0	55800000.0	47594000.0	42050000.0	5061000.0	18173000.0	44713000.0	18973000.0	12260000.0
1997	78481000.0	107242000.0	55800000.0	47594000.0	45957000.0	5324000.0	40196000.0	48610000.0	19111000.0	11182000.0
1998	82758000.0	107927000.0	69200000.0	47594000.0	50872000.0	8426000.0	42431000.0	49328000.0	17648000.0	10635000.0
1999	84540000.0	117383000.0	78100000.0	53144000.0	53881000.0	9232000.0	42390000.0	55097000.0	18368000.0	12631000.0
2000	87973000.0	127268000.0	80507000.0	58901000.0	56837000.0	10473000.0	44628000.0	56677000.0	19182000.0	18371000.0
2001	84755000.0	123732000.0	81551000.0	61096000.0	58281000.0	12133000.0	43611000.0	53122000.0	18359000.0	18030000.0
2002	80883000.0	124633000.0	80393000.0	64540000.0	59377000.0	16602000.0	44660000.0	45043000.0	17705000.0	20428000.0
2003	75880000.0	123015000.0	85345000.0	60936000.0	61424000.0	20222000.0	46357000.0	38730000.0	17739000.0	20572000.0
2004	79655000.0	128903000.0	84859000.0	68903000.0	64194000.0	28853000.0	40400000.0	37226000.0	19595000.0	24507000.0
2005	79215000.0	128392000.0	86622000.0	72300000.0	66494000.0	31026000.0	43407000.0	40841000.0	21099000.0	28416000.0
2006	148511000.0	122022000.0	81801000.0	75812000.0	69536000.0	34524000.0	46369000.0	44696000.0	46912000.0	29107000.0
2007	140364000.0	109540000.0	82099000.0	80682000.0	69450000.0	40954000.0	49166000.0	47561000.0	50044000.0	34285000.0
2008	136148000.0	107519000.0	86201000.0	81911000.0	69011000.0	45844000.0	54421000.0	50243000.0	51737000.0	36538000.0
2009	129954000.0	98228000.0	85547000.0	81958000.0	63513000.0	47656000.0	54839000.0	39270000.0	47481000.0	34276000.0
2010	121574000.0	91658000.0	85872000.0	84442000.0	64647000.0	57386000.0	55304000.0	42760000.0	53620000.0	39323000.0
2011	114089000.0	88113000.0	84692000.0	84816000.0	67493000.0	70250000.0	52617000.0	43270000.0	61909000.0	43726000.0
2012	116329000.0	87332000.0	82729000.0	85276000.0	66858000.0	83182000.0	53338000.0	48290000.0	65175000.0	47813000.0
2013	118968000.0	90787000.0	87459000.0	84414000.0	68959000.0	98185000.0	52633000.0	52580000.0	65780000.0	54069000.0
2014	121699000.0	90982000.0	83008000.0	84519000.0	72204000.0	116593000.0	55169000.0	35400000.0	63737000.0	45889000.0
2015	130364000.0	94988000.0	83737000.0	89082000.0	77619000.0	127860000.0	57418000.0	44300000.0	55971000.0	34550000.0
2016	141526000.0	97372000.0	90966000.0	91758000.0	81757000.0	135130000.0	57480000.0	44500000.0	52979000.0	31659000.0
2017	148045000.0	94274000.0	92402000.0	91304000.0	87242000.0	143035000.0	60042000.0	46700000.0	54955000.0	39629000.0
2018	158445400.0	86280000.0	108542000.0	92214000.0	90571000.0	149720000.0	61194600.0	48600000.0	38069000.0	41964000.0
2019	170930100.0	82752000.0	99533000.0	94715000.0	93086000.0	154632000.0	62207000.0	50600000.0	37845900.0	45330000.0

name	France	United States of America	China	Mexico	Spain	Poland	Italy	Croatia	Hungary	Canada
year
1995	60033000.0	79732000.0	46387000.0	85446000.0	52460000.0	82244000.0	55706000.0	16100000.0	39240000.0	41657000.0
1996	148263000.0	82756000.0	51128000.0	90394000.0	55077000.0	87439000.0	59805000.0	19085000.0	39833000.0	43256000.0
1997	157551000.0	82525000.0	57588000.0	92915000.0	62415000.0	87817000.0	57998000.0	23660000.0	37315000.0	45076000.0
1998	70109000.0	74767000.0	63478000.0	95214000.0	68068000.0	88592000.0	58499000.0	25499000.0	33624000.0	48064000.0
1999	73147000.0	75796000.0	72796000.0	99869000.0	72040000.0	89118000.0	59521000.0	29215000.0	28803000.0	49055000.0
2000	77190000.0	78343000.0	83444000.0	105673000.0	74580000.0	84515000.0	62702000.0	37226000.0	31141000.0	48638000.0
2001	75202000.0	70975000.0	89013000.0	100718000.0	75564000.0	61431000.0	60960000.0	40129000.0	30679000.0	47147000.0
2002	77012000.0	64434000.0	97908000.0	100153000.0	79313000.0	50735000.0	63561000.0	41737000.0	31739000.0	44896000.0
2003	75048000.0	62082000.0	91662000.0	92330000.0	82326000.0	52130000.0	63026000.0	42857000.0	31412000.0	38903000.0
2004	190282000.0	67606000.0	109038000.0	99250000.0	85981000.0	61918000.0	58480000.0	44974000.0	33934000.0	38845000.0
2005	185829000.0	71484000.0	120292000.0	103146000.0	92563000.0	64606000.0	59230000.0	45762000.0	36173000.0	36160000.0
2006	193882000.0	183178000.0	124942000.0	97701000.0	96152000.0	65115000.0	66353000.0	47733000.0	38318000.0	33390000.0
2007	193319000.0	175299000.0	131873000.0	93582000.0	98907000.0	66208000.0	70271000.0	52271000.0	39379000.0	30373000.0
2008	193571000.0	175703000.0	130027000.0	92948000.0	97670000.0	59935000.0	70719000.0	51336000.0	39554000.0	27370000.0
2009	192369000.0	160508000.0	126476000.0	88044000.0	91899000.0	53840000.0	71692000.0	47573000.0	40624000.0	24696000.0
2010	189826000.0	162275000.0	133762000.0	81953000.0	93744000.0	58340000.0	73225000.0	49006000.0	39904000.0	25621000.0
2011	196595000.0	147271416.0	135423000.0	75732000.0	99187000.0	60745000.0	75866000.0	49969000.0	41304000.0	25066000.0
2012	197522000.0	171629897.0	132405000.0	76749000.0	98128000.0	67390000.0	76293000.0	47185000.0	43565000.0	25318000.0
2013	204410000.0	179309907.0	129078000.0	78100000.0	103231000.0	72310000.0	76762000.0	48345000.0	43611000.0	25167000.0
2014	206599000.0	178311354.0	128499000.0	81042000.0	107144000.0	73750000.0	77694000.0	51168000.0	45984000.0	25558000.0
2015	203302000.0	176864526.0	133820000.0	87129000.0	109834000.0	77743000.0	81068000.0	55858000.0	48345000.0	27555000.0
2016	203042000.0	175261488.0	141774000.0	94853000.0	115561000.0	80476000.0	84925000.0	57587000.0	52890000.0	30142000.0
2017	207274000.0	174291746.0	153260000.0	99349000.0	121717000.0	83804000.0	89931000.0	59238000.0	54962000.0	31081000.0
2018	211998000.0	169324918.0	158606000.0	96497000.0	124456000.0	85946000.0	93228600.0	57668000.0	57667000.0	31274000.0
2019	217877000.0	165478000.0	162538000.0	97406000.0	126170000.0	88515000.0	95399000.0	60021000.0	61397000.0	32430000.0

name	China	United States of America	India	United Kingdom	Japan	Spain	Canada	Indonesia	France	Australia
year
1995	6.290000e+08	2.004500e+09	1.366440e+08	1.260100e+08	734558000.0	1.154560e+08	208165000.0	200589000.0	210755000.0	243920000.0
1996	6.400000e+08	2.004500e+09	1.401200e+08	1.260100e+08	734558000.0	1.154560e+08	208165000.0	200589000.0	210755000.0	243920000.0
1997	6.440000e+08	2.004500e+09	1.598770e+08	1.260100e+08	734558000.0	1.154560e+08	208165000.0	200589000.0	210755000.0	243920000.0
1998	6.950000e+08	2.004500e+09	1.681960e+08	1.260100e+08	734558000.0	1.154560e+08	208165000.0	200589000.0	210755000.0	243920000.0
1999	7.190000e+08	2.004500e+09	1.906710e+08	1.260100e+08	734558000.0	1.154560e+08	208165000.0	200589000.0	210755000.0	243920000.0
2000	7.440000e+08	2.004500e+09	2.201070e+08	1.260100e+08	734558000.0	3.710172e+08	208165000.0	200589000.0	210755000.0	235235000.0
2001	7.840000e+08	2.004500e+09	2.364700e+08	1.260100e+08	734558000.0	4.052927e+08	208165000.0	200589000.0	210755000.0	220593000.0
2002	8.780000e+08	2.004500e+09	2.695980e+08	1.260100e+08	734558000.0	4.029999e+08	208165000.0	200589000.0	210755000.0	217472000.0
2003	8.700000e+08	2.004500e+09	3.090380e+08	1.260100e+08	734558000.0	4.326621e+08	208165000.0	200589000.0	210755000.0	212681000.0
2004	1.102000e+09	2.004500e+09	3.662680e+08	1.260100e+08	734558000.0	4.156371e+08	208165000.0	200589000.0	210755000.0	203869000.0
2005	1.212000e+09	2.004500e+09	3.920140e+08	1.260100e+08	734558000.0	1.570054e+08	208165000.0	200589000.0	210755000.0	200044000.0
2006	1.394000e+09	2.004500e+09	4.623210e+08	1.260100e+08	734558000.0	1.549684e+08	208165000.0	204553000.0	284337000.0	208028000.0
2007	1.610000e+09	2.004500e+09	5.265640e+08	1.260100e+08	734558000.0	3.555545e+08	214559000.0	222389000.0	288609000.0	223980000.0
2008	1.712000e+09	1.964900e+09	5.630340e+08	1.260100e+08	734558000.0	3.929012e+08	214498000.0	225041000.0	278950000.0	210754000.0
2009	1.902000e+09	1.900100e+09	6.688000e+08	1.260100e+08	702896000.0	3.652531e+08	227121000.0	229730000.0	278275000.0	215846000.0
2010	2.103000e+09	1.963700e+09	7.477000e+08	1.194340e+08	631596000.0	3.544248e+08	229158000.0	234377000.0	268041000.0	225239000.0
2011	2.641000e+09	1.998500e+09	8.645330e+08	1.668640e+09	612525000.0	3.476951e+08	317021000.0	236751000.0	276752000.0	233127000.0
2012	2.957000e+09	2.030300e+09	1.045050e+09	1.836020e+09	612750000.0	3.728110e+08	316254000.0	245290000.0	268673000.0	248377000.0
2013	3.262000e+09	2.059600e+09	1.142529e+09	1.710905e+09	630950000.0	3.984230e+08	320266300.0	250036000.0	265182000.0	240118000.0
2014	3.611000e+09	2.109300e+09	1.282802e+09	1.698942e+09	595221000.0	4.627610e+08	318208700.0	251237000.0	266027000.0	260362000.0
2015	3.990000e+09	2.178700e+09	1.431974e+09	1.649626e+09	604715000.0	3.722650e+08	315745700.0	256419000.0	256078000.0	269481000.0
2016	4.435000e+09	2.206500e+09	1.615389e+09	1.953655e+09	641079000.0	3.971340e+08	319315000.0	264338000.0	255498000.0	280325000.0
2017	5.010000e+09	2.248700e+09	1.657546e+09	1.914076e+09	647510000.0	4.483050e+08	325808200.0	270822000.0	276537000.0	291797000.0
2018	5.539000e+09	2.291100e+09	1.853788e+09	1.821956e+09	561779000.0	4.464790e+08	278060000.0	303403000.0	268152000.0	310166000.0
2019	6.005852e+09	2.326623e+09	2.321983e+09	1.776080e+09	587103000.0	4.235720e+08	275418000.0	722159000.0	260522000.0	365797000.0

	index	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019
0	Afghanistan	73.684211	61.403509	61.403509	55.263158	61.403509	91.228070	100.000000	84.210526	80.701754	64.912281	59.649123	54.385965	56.140351	57.017544	64.912281	92.105263
1	Åland Islands	100.000000	16.358025	85.493827	24.382716	20.370370	32.716049	30.864198	37.037037	35.802469	45.370370	31.790123	45.679012	46.913580	45.679012	48.148148	49.691358
2	Albania	61.878453	61.049724	54.972376	59.944751	70.441989	77.348066	74.033149	74.033149	70.994475	70.441989	80.662983	78.729282	96.685083	88.397790	85.911602	100.000000
3	American Samoa	99.076923	84.615385	68.615385	62.769231	63.692308	100.000000	66.769231	53.846154	57.846154	45.230769	47.692308	53.230769	62.461538	50.461538	52.923077	56.923077
4	Andorra	100.000000	90.643275	76.842105	65.964912	56.374269	52.280702	46.432749	40.701754	39.064327	39.532164	36.959064	40.116959	37.076023	40.818713	39.766082	50.643275
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
222	United Kingdom of Great Britain and Northern I...	33.590734	93.050193	71.235521	76.254826	75.289575	82.625483	79.343629	67.181467	86.872587	91.505792	89.189189	86.293436	92.084942	94.594595	100.000000	88.610039
223	United States of America	100.000000	76.660342	56.925996	55.977230	57.495256	44.402277	39.848197	34.345351	32.637571	29.222011	29.222011	30.740038	27.514231	27.134725	43.453510	24.667932
224	United States Minor Outlying Islands	93.750000	41.666667	100.000000	71.875000	55.208333	68.229167	58.333333	53.645833	51.041667	47.395833	58.854167	55.729167	64.583333	60.937500	65.625000	83.333333
225	Viet Nam	15.515409	15.515409	14.877790	19.659936	34.112646	71.307120	96.811902	100.000000	91.710946	80.340064	86.078640	80.871413	70.350691	51.115834	47.608927	39.319872
226	Zimbabwe	77.339901	75.615764	61.330049	63.793103	85.221675	62.068966	61.330049	69.704433	70.197044	84.729064	80.788177	100.000000	96.551724	99.753695	94.581281	80.788177

	name	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019
0	France	87.334597	85.290783	88.986905	88.728503	88.844164	88.292477	87.125305	90.232103	90.657573	93.818990	94.823685	93.310446	93.191112	95.133493	97.301689	100.000000
1	United States of America	36.907271	39.024337	100.000000	95.698719	95.919270	87.624060	88.588695	80.397982	93.695693	97.888342	97.343215	96.553367	95.678241	95.148842	92.437366	90.337268
2	China	67.084620	74.008540	76.869409	81.133643	79.997908	77.813188	82.295832	83.317747	81.460951	79.414045	79.057820	82.331516	87.225141	94.291796	97.580873	100.000000
3	Mexico	96.222830	100.000000	94.721075	90.727706	90.113044	85.358618	79.453396	73.422139	74.408121	75.717914	78.570182	84.471526	91.959940	96.318810	93.553798	94.435073
4	Spain	68.146945	73.363716	76.208290	78.391852	77.411429	72.837442	74.299754	78.613775	77.774431	81.818974	84.920346	87.052390	91.591504	96.470635	98.641515	100.000000
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
195	São Tomé and Príncipe	30.372493	45.272206	35.243553	33.810888	41.547278	43.553009	22.922636	34.957020	34.957020	34.957020	34.957020	73.352436	82.808023	82.808023	95.702006	100.000000
196	Montserrat	78.756477	67.875648	49.222798	45.077720	43.523316	37.823834	39.896373	38.341969	51.321244	45.077720	55.440415	68.911917	69.948187	96.373057	86.528497	100.000000
197	Marshall Islands	97.826087	100.000000	63.043478	78.260870	65.217391	58.695652	50.000000	50.000000	50.000000	50.000000	53.260870	68.478261	70.652174	85.869565	73.913043	66.304348
198	Niue	22.413793	24.137931	25.862069	30.172414	40.517241	40.517241	53.448276	52.586207	43.103448	60.344828	63.793103	66.379310	76.724138	100.000000	90.517241	87.931034
199	Tuvalu	35.135135	29.729730	29.729730	29.729730	45.945946	43.243243	45.945946	32.432432	29.729730	35.135135	37.837838	64.864865	67.567568	67.567568	83.783784	100.000000

	inbound tourism	interest over time
2004	10.068686	61.878453
2005	11.676553	61.049724
2006	14.626912	54.972376
2007	17.592882	59.944751
2008	22.166719	70.441989
2009	28.972838	77.348066
2010	37.730253	74.033149
2011	45.769591	74.033149
2012	54.854824	70.994475
2013	50.827349	70.441989
2014	57.336872	80.662983
2015	64.486419	78.729282
2016	73.930690	96.685083
2017	79.893850	88.397790
2018	92.522635	85.911602
2019	100.000000	100.000000

Popularity of Tourism in Various Countries before the COVID-19 Pandemic by Lee Care Greene¶

Table of Content (with relevant hyperlinks to sections)¶

Motivation and Background¶

Summary of Research Questions & Results¶

Dataset¶

Methodology¶

Data Acquisition¶

Data Cleaning¶

EDA¶

1. Which countries have the highest number of outbound tourism, inbound tourism, and domestic tourism?¶

i. Outbound tourism (departures)¶

ii. Inbound tourism (arrivals)¶

iii. Domestic tourism (trips)¶

2. What is the country with the most visits (e.g. sum of inbound tourism and domestic tourism)?¶

3. What are the countries with the most tourism in every region?¶

i. Outbound tourism (departures)¶

ii. Inbound tourism (arrivals)¶

iii. Domestic tourism (trips)¶

iv. Arrivals¶

v. Total¶

4. Which country has the most tourism overall (e.g. sum of outbound tourism, inbound tourism, and domestic tourism)?¶

5. How did tourism grow across various countries?¶

i. Outbound tourism (departures)¶

ii. Inbound tourism (arrivals)¶

iii. Domestic tourism (trips)¶

6. Are there any correlations between tourism of countries / regions and other variables (heritage, interest over time, etc.)?¶

i. Rankings of Countries¶

ii. Interest over time¶

iii. Area¶

Results Findings & Conclusion¶

1. Which countries have the highest number of outbound tourism, inbound tourism, and domestic tourism?¶

i. Outbound tourism (departures)¶

ii. Inbound tourism (arrivals)¶

iii. Domestic tourism (trips)¶

2. What is the country with the most visits (e.g. sum of inbound tourism and domestic tourism)?¶

3. What are the countries with the most tourism in every region?¶

i. Outbound tourism (departures)¶

ii. Inbound tourism (arrivals)¶

iii. Domestic tourism (trips)¶

iv. Arrivals¶

v. Total¶

4. Which country has the most tourism overall (e.g. sum of outbound tourism, inbound tourism, and domestic tourism)?¶

5. How did tourism grow across various countries?¶

i. Outbound tourism (departures)¶

ii. Inbound tourism (arrivals)¶

iii. Domestic tourism (trips)¶

6. Are there any correlations between tourism of countries / regions and other variables (heritage, interest over time, etc.)?¶

i. Rankings of Countries¶

ii. Interest over time¶

iii. Area¶

Recommendations or Further Works¶

References¶

Motivation and Background ¶

Summary of Research Questions & Results ¶

Dataset ¶

Methodology ¶

Data Acquisition ¶

Data Cleaning ¶

EDA ¶

Results Findings & Conclusion ¶

Recommendations or Further Works ¶

References ¶